metadata

library_name: transformers
base_model: layoutlmv3
tags:
  - generated_from_trainer
datasets:
  - mp-02/sroie
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-base-sroie
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: mp-02/sroie
          type: mp-02/sroie
        metrics:
          - name: Precision
            type: precision
            value: 0.9469573706475757
          - name: Recall
            type: recall
            value: 0.9648541114058355
          - name: F1
            type: f1
            value: 0.9558219740515684
          - name: Accuracy
            type: accuracy
            value: 0.9863575751359114

layoutlmv3-base-sroie

This model is a fine-tuned version of layoutlmv3 on the mp-02/sroie dataset. It achieves the following results on the evaluation set:

Loss: 0.0526
Precision: 0.9470
Recall: 0.9649
F1: 0.9558
Accuracy: 0.9864

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 3000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.5	100	0.0806	0.9001	0.9377	0.9185	0.9759
No log	5.0	200	0.0541	0.9392	0.9576	0.9483	0.9840
No log	7.5	300	0.0515	0.9368	0.9629	0.9496	0.9844
No log	10.0	400	0.0515	0.9450	0.9622	0.9535	0.9856
0.0717	12.5	500	0.0526	0.9470	0.9649	0.9558	0.9864
0.0717	15.0	600	0.0558	0.9353	0.9685	0.9516	0.9849
0.0717	17.5	700	0.0668	0.9408	0.9635	0.9520	0.9852

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1